# UWB-NTIS Speaker Diarization System for the DIHARD II 2019 Challenge

## TL;DR

This paper describes a speaker diarization system developed for the DIHARD II challenge, utilizing standard segmentation, i/x-vector extraction, clustering, and resegmentation, with hyperparameters tuned via a domain classifier.

## Contribution

The paper introduces a domain-adaptive diarization system that combines standard methods with hyperparameter optimization based on a domain classifier for improved performance.

## Key findings

- Achieved a DER of 23.47% on the evaluation set.
- Compared and combined with Kaldi diarization results.
- Demonstrated effectiveness of domain-specific hyperparameter tuning.

## Abstract

In this paper, we present our system developed by the team from the New Technologies for the Information Society (NTIS) research center of the University of West Bohemia in Pilsen, for the Second DIHARD Speech Diarization Challenge. The base of our system follows the currently-standard approach of segmentation, i/x-vector extraction, clustering, and resegmentation. The hyperparameters for each of the subsystems were selected according to the domain classifier trained on the development set of DIHARD II. We compared our system with results from the Kaldi diarization (with i/x-vectors) and combined these systems. At the time of writing of this abstract, our best submission achieved a DER of 23.47% and a JER of 48.99% on the evaluation set (in Track 1 using reference SAD).